Published on

Published in: Education, Automotive, Technology
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide
  • Your will give additional explanation for each approach?
  • Lpr2003

    1. 1. Automatic License Plate Recognition System
    2. 2. Introduction <ul><li>A License Plate Recognition System (LPRS) is a system to automatically detect, recognize and identify a vehicle plate. </li></ul><ul><li>Vehicle license plate (VLP) constitutes an unambiguous identifier of a vehicle participating in road traffic. Reading a license plate is the first step in determining the identities of parties involved in traffic incidents. </li></ul>
    3. 3. <ul><li>License-Plate Recognition System consists of three main modules: </li></ul><ul><li> License plate detection, </li></ul><ul><li> character segmentation and </li></ul><ul><li> Optical Character Recognition (OCR). </li></ul>
    4. 4. Flow chart Start Input Image License Plate Extraction Character Segmentation Character Identification Display Plate Number End
    5. 5. License Plate Detection <ul><li>Preprocessing : T he first step is to identify the regions in the image that contain the intensity of RGB corresponding to the color yellow </li></ul><ul><li>Morphological operation : These are Non-linear filters, with the function of restraining noises, extracting features and segmenting images etc </li></ul><ul><li>Horizontal segmentation : It will give the width and the x coordinates of the potentially candidates regions. </li></ul>
    6. 6. <ul><li>Vertical segmentation : It will give the Height and the y coordinates of the potentially candidates regions </li></ul><ul><li>Identifying License Plate : T wo features are defined and extracted in order to decide if a candidate region contains a license plate or not , these features are: </li></ul><ul><li>1. Aspect ratio </li></ul><ul><li>2. Edge Density </li></ul>
    7. 7. Character segmentation <ul><li>Conversion to gray scale. </li></ul><ul><li>Binarization. </li></ul><ul><li>Horizontal segmentation. </li></ul><ul><li>Vertical Segmentation. </li></ul>
    8. 8. Optical Character Recognition(OCR) <ul><li>Training : The program is first trained with a set of sample images for each of the characters to extract the important features based on which the recognition operation would be performed. </li></ul><ul><li>The program must be trained on a set of 10 characters with 10 samples of each. The training algorithm involves the following steps: </li></ul><ul><li> Preprocessing. </li></ul><ul><li> Template creation. </li></ul>
    9. 9. <ul><li>Recognition : </li></ul><ul><li> Preprocessing. </li></ul><ul><li> Template matching : C alculate the matching score of the segmented character from the templates of the character stored by the following algorithm. </li></ul><ul><li>Compare the pixel values of the matrix of segmented character and the template matrix, and for every match we add 1 to the matching score and for every mis-match we decrement 1. This is done for all 225 pixels. The match score is generated for every template and the one which gives the highest score is taken to be the recognized character </li></ul>
    10. 10. Applications <ul><li>computerized road traffic monitoring systems </li></ul><ul><li>electronic fee collection solutions, </li></ul><ul><li>surveillance devices </li></ul><ul><li>safety supervision systems </li></ul>
    11. 11. Previous Work <ul><li>Many difference solutions have already been proposed for each stage of recognition </li></ul><ul><li>Plate localization </li></ul><ul><ul><li>Use edge statistics to locate the plate </li></ul></ul><ul><ul><li>Fuzzy clustering algorithms </li></ul></ul>
    12. 12. Previous Work <ul><li>Character Segmentation </li></ul><ul><ul><li>Vertical/horizontal projection </li></ul></ul><ul><ul><li>Adaptive Clustering </li></ul></ul><ul><li>Optical Character Recognition </li></ul><ul><ul><li>Template matching </li></ul></ul><ul><ul><li>Neural network </li></ul></ul><ul><ul><li>Feature analysis </li></ul></ul>
    13. 13. References <ul><li>Automatic Vehicle License-Plate Recognition System By Deepak Kumar Gupta-Y6154 and Siddhartha Kandoi-Y6472 </li></ul><ul><li>Combining Hough Transform and Contour Algorithm for detecting Vehicles. License-Plates - Tran Duc Duan, Duong Anh Duc, Tran Le Hong Du – October 2004 </li></ul><ul><li>Building an Automatic Vehicle License-Plate Recognition System - Tran Duc Duan, Tran Le Hong Du, Tran Vinh Phuoc, Nguyen Viet Hoang – Febraury 2005 </li></ul><ul><li>A High Accurate Macau License Plate Recognition System - CheokMan , Kengchung - 2008 </li></ul><ul><li>Rectangular Object Tracking Based on Standard Hough Transform - Thuy Tuong Nguyen, Xuan Dai Pham and Jae Wook Jeon, - February, 2009 </li></ul><ul><li>A New Algorithm for Character Segmentation of License Plate - Yungang Zhang Changshui Zhang - June 2003 </li></ul><ul><li>Mean Shift for Accurate Number Plate Detection - Wenjing Jia, Huaifeng Zhang, and Xiangjian He - July 2005 </li></ul>